import json
import copy
import time
import random
import numpy as np
import torch
import torch.nn as nn
import torch.optim as optim
import matplotlib.pyplot as plt
from matplotlib import pyplot as plt
from torchsummary import summary
from nmfd_gnn import NMFD_GNN
print (torch.cuda.is_available())
device = torch.device("cuda:0")
random_seed = 42
random.seed(random_seed)
torch.manual_seed(random_seed)
torch.cuda.manual_seed(random_seed)
r = random.random
True
#1.1: settings
M = 20 #number of time interval in a window
missing_ratio = 0.50
file_name = "m_" + str(M) + "_missing_" + str(int(missing_ratio*100))
print (file_name)
#1.2: hyperparameters
num_epochs, batch_size, learning_rate = 200, 16, 0.001
beta_flow, beta_occ, beta_phy = 1.0, 1.0, 0.1
batch_size_vt = 16 #batch size for evaluation and test
hyper = {"n_e": num_epochs, "b_s": batch_size, "b_s_vt": batch_size_vt, "l_r": learning_rate,\
"beta_f": beta_flow, "beta_o": beta_occ, "beta_p": beta_phy}
gnn_dim_1, gnn_dim_2, gnn_dim_3, lstm_dim = 2, 128, 128, 128
p_dim = 10 #column dimension of L1, L2
c_k = 5.5 #meter, the sum of loop width and uniform vehicle length. based on Gero and Daganzo 2008.
theta_ini = [-2.757, 4.996, -2.409, 1.638, 3.569]
hyper_model = {"g_dim_1": gnn_dim_1, "g_dim_2": gnn_dim_2, "g_dim_3": gnn_dim_3, "l_dim": lstm_dim,\
"p_dim": p_dim, "c_k": c_k, "theta_ini": theta_ini}
max_no_decrease = 30
#1.3: set paths
root_path = "/home/umni2/a/umnilab/users/xue120/umni4/2023_mfd_traffic/"
file_path = root_path + "2_prepare_data/" + file_name + "/"
train_path, vali_path, test_path =\
file_path + "train.json", file_path + "vali.json", file_path + "test.json"
sensor_id_path = file_path + "sensor_id_order.json"
sensor_adj_path = file_path + "sensor_adj.json"
mean_std_path = file_path + "mean_std.json"
m_20_missing_50
def visualize_train_loss(total_phy_flow_occ_loss):
plt.figure(figsize=(4,3), dpi=75)
t_p_f_o_l = np.array(total_phy_flow_occ_loss)
e_loss, p_loss, f_loss, o_loss = t_p_f_o_l[:,0], t_p_f_o_l[:,1], t_p_f_o_l[:,2], t_p_f_o_l[:,3]
x = range(len(e_loss))
plt.plot(x, p_loss, linewidth=1, label = "phy loss")
plt.plot(x, f_loss, linewidth=1, label = "flow loss")
plt.plot(x, o_loss, linewidth=1, label = "occ loss")
plt.legend()
plt.title('Loss decline on train')
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.savefig(file_name + '/' + 'train_loss.png', bbox_inches = 'tight')
plt.show()
def visualize_flow_loss(vali_f_mae, test_f_mae):
plt.figure(figsize=(4,3), dpi=75)
x = range(len(vali_f_mae))
plt.plot(x, vali_f_mae, linewidth=1, label="Validate")
plt.plot(x, test_f_mae, linewidth=1, label="Test")
plt.legend()
plt.title('MAE of flow on validate/test')
plt.xlabel('Epoch')
plt.ylabel('MAE (veh/h)')
plt.savefig(file_name + '/' + 'flow_mae.png', bbox_inches = 'tight')
plt.show()
def visualize_occ_loss(vali_o_mae, test_o_mae):
plt.figure(figsize=(4,3), dpi=75)
x = range(len(vali_o_mae))
plt.plot(x, vali_o_mae, linewidth=1, label="Validate")
plt.plot(x, test_o_mae, linewidth=1, label="Test")
plt.legend()
plt.title('MAE of occupancy on validate/test')
plt.xlabel('Epoch')
plt.ylabel('MAE')
plt.savefig(file_name + '/' + 'occ_mae.png',bbox_inches = 'tight')
plt.show()
def MAELoss(yhat, y):
return float(torch.mean(torch.div(torch.abs(yhat-y), 1)))
def RMSELoss(yhat, y):
return float(torch.sqrt(torch.mean((yhat-y)**2)))
def vali_test(model, f, f_mask, o, o_mask, f_o_mean_std, b_s_vt):
flow_std, occ_std, n = f_o_mean_std[1], f_o_mean_std[3], len(f)
f_mae_list, f_rmse_list, o_mae_list, o_rmse_list, num_list = list(), list(), list(), list(), list()
for i in range(0, n, b_s_vt):
s, e = i, np.min([i+b_s_vt, n])
num_list.append(e-s)
bf, bo, bf_mask, bo_mask = f[s: e], o[s: e], f_mask[s: e], o_mask[s: e]
bf_hat, bo_hat, bq_hat, bq_theta = model.run(bf_mask, bo_mask)
bf_hat, bo_hat = bf_hat.cpu(), bo_hat.cpu()
bf_mae, bf_rmse = MAELoss(bf_hat, bf)*flow_std, RMSELoss(bf_hat, bf)*flow_std
bo_mae, bo_rmse = MAELoss(bo_hat, bo)*occ_std, RMSELoss(bo_hat, bo)*occ_std
f_mae_list.append(bf_mae)
f_rmse_list.append(bf_rmse)
o_mae_list.append(bo_mae)
o_rmse_list.append(bo_rmse)
f_mae, o_mae = np.dot(f_mae_list, num_list)/n, np.dot(o_mae_list, num_list)/n
f_rmse = np.sqrt(np.dot(np.multiply(f_rmse_list, f_rmse_list), num_list)/n)
o_rmse = np.sqrt(np.dot(np.multiply(o_rmse_list, o_rmse_list), num_list)/n)
return f_mae, f_rmse, o_mae, o_rmse
def evaluate(model, vt_f, vt_o, vt_f_m, vt_o_m, f_o_mean_std, b_s_vt): #vt: vali_test
vt_f_mae, vt_f_rmse, vt_o_mae, vt_o_rmse =\
vali_test(model, vt_f, vt_f_m, vt_o, vt_o_m, f_o_mean_std, b_s_vt)
return vt_f_mae, vt_f_rmse, vt_o_mae, vt_o_rmse
#4.1: one training epoch
def train_epoch(model, opt, criterion, train_f_x, train_f_y, train_o_x, train_o_y, hyper, flow_std_squ):
#f: flow; o: occupancy
model.train()
losses, p_losses, f_losses, o_losses = list(), list(), list(), list()
beta_f, beta_o, beta_p, b_s = hyper["beta_f"], hyper["beta_o"], hyper["beta_p"], hyper["b_s"]
n = len(train_f_x)
print ("# batch: ", int(n/b_s))
for i in range(0, n-b_s, b_s):
time1 = time.time()
x_f_batch, y_f_batch = train_f_x[i: i+b_s], train_f_y[i: i+b_s]
x_o_batch, y_o_batch = train_o_x[i: i+b_s], train_o_y[i: i+b_s]
opt.zero_grad()
y_f_hat, y_o_hat, q_hat, q_theta = model.run(x_f_batch, x_o_batch)
p_loss = criterion(q_hat, q_theta).cpu() #physical loss
p_loss = p_loss/flow_std_squ
f_loss = criterion(y_f_hat.cpu(), y_f_batch) #data loss of flow
o_loss = criterion(y_o_hat.cpu(), y_o_batch) #data loss of occupancy
loss = beta_f*f_loss + beta_o*o_loss + beta_p*p_loss
loss.backward()
opt.step()
losses.append(loss.data.numpy())
p_losses.append(p_loss.data.numpy())
f_losses.append(f_loss.data.numpy())
o_losses.append(o_loss.data.numpy())
if i % (64*b_s) == 0:
print ("i_batch: ", i/b_s)
print ("the loss for this batch: ", loss.data.numpy())
print ("flow loss", f_loss.data.numpy())
print ("occ loss", o_loss.data.numpy())
time2 = time.time()
print ("time for this batch", time2-time1)
print ("----------------------------------")
n_loss = float(len(losses)+0.000001)
aver_loss = sum(losses)/n_loss
aver_p_loss = sum(p_losses)/n_loss
aver_f_loss = sum(f_losses)/n_loss
aver_o_loss = sum(o_losses)/n_loss
return aver_loss, model, aver_p_loss, aver_f_loss, aver_o_loss
#4.2: all train epochs
def train_process(model, criterion, train, vali, test, hyper, f_o_mean_std):
total_phy_flow_occ_loss = list()
n_mse_flow_occ = 0 #mse(flow) + mse(occ) for validation sets.
vali_f, vali_o = vali["flow"], vali["occupancy"]
vali_f_m, vali_o_m = vali["flow_mask"].to(device), vali["occupancy_mask"].to(device)
test_f, test_o = test["flow"], test["occupancy"]
test_f_m, test_o_m = test["flow_mask"].to(device), test["occupancy_mask"].to(device)
l_r, n_e = hyper["l_r"], hyper["n_e"]
opt = optim.Adam(model.parameters(), l_r, betas = (0.9,0.999), weight_decay=0.0001)
opt_scheduler = torch.optim.lr_scheduler.MultiStepLR(opt, milestones=[150])
print ("# epochs ", n_e)
r_vali_f_mae, r_vali_o_mae, r_test_f_mae, r_test_o_mae = list(), list(), list(), list()
r_vali_f_rmse, r_vali_o_rmse, r_test_f_rmse, r_test_o_rmse = list(), list(), list(), list()
flow_std_squ = np.power(f_o_mean_std[1], 2)
no_decrease = 0
for i in range(n_e):
print ("----------------an epoch starts-------------------")
#time1_s = time.time()
time_s = time.time()
print ("i_epoch: ", i)
n_train = len(train["flow"])
number_list = copy.copy(list(range(n_train)))
random.shuffle(number_list, random = r)
shuffle_idx = torch.tensor(number_list)
train_x_f, train_y_f = train["flow_mask"][shuffle_idx], train["flow"][shuffle_idx]
train_x_o, train_y_o = train["occupancy_mask"][shuffle_idx], train["occupancy"][shuffle_idx]
aver_loss, model, aver_p_loss, aver_f_loss, aver_o_loss =\
train_epoch(model, opt, criterion, train_x_f.to(device), train_y_f,\
train_x_o.to(device), train_y_o, hyper, flow_std_squ)
opt_scheduler.step()
total_phy_flow_occ_loss.append([aver_loss, aver_p_loss, aver_f_loss, aver_o_loss])
print ("train loss for this epoch: ", round(aver_loss, 6))
#evaluate
b_s_vt = hyper["b_s_vt"]
vali_f_mae, vali_f_rmse, vali_o_mae, vali_o_rmse =\
evaluate(model, vali_f, vali_o, vali_f_m, vali_o_m, f_o_mean_std, b_s_vt)
test_f_mae, test_f_rmse, test_o_mae, test_o_rmse =\
evaluate(model, test_f, test_o, test_f_m, test_o_m, f_o_mean_std, b_s_vt)
r_vali_f_mae.append(vali_f_mae)
r_test_f_mae.append(test_f_mae)
r_vali_o_mae.append(vali_o_mae)
r_test_o_mae.append(test_o_mae)
r_vali_f_rmse.append(vali_f_rmse)
r_test_f_rmse.append(test_f_rmse)
r_vali_o_rmse.append(vali_o_rmse)
r_test_o_rmse.append(test_o_rmse)
visualize_train_loss(total_phy_flow_occ_loss)
visualize_flow_loss(r_vali_f_mae, r_test_f_mae)
visualize_occ_loss(r_vali_o_mae, r_test_o_mae)
time_e = time.time()
print ("time for this epoch", time_e - time_s)
performance = {"train": total_phy_flow_occ_loss,\
"vali": [r_vali_f_mae, r_vali_f_rmse, r_vali_o_mae, r_vali_o_rmse],\
"test": [r_test_f_mae, r_test_f_rmse, r_test_o_mae, r_test_o_rmse]}
subfile = open(file_name + '/' + 'performance'+'.json','w')
json.dump(performance, subfile)
subfile.close()
#early stop
flow_std, occ_std = f_o_mean_std[1], f_o_mean_std[3]
norm_f_rmse, norm_o_rmse = vali_f_rmse/flow_std, vali_o_rmse/occ_std
norm_sum_mse = norm_f_rmse*norm_f_rmse + norm_o_rmse*norm_o_rmse
if n_mse_flow_occ > 0:
min_until_now = min([min_until_now, norm_sum_mse])
else:
min_until_now = 1000000.0
if norm_sum_mse > min_until_now:
no_decrease = no_decrease+1
else:
no_decrease = 0
if no_decrease == max_no_decrease:
print ("Early stop at the " + str(i+1) + "-th epoch")
return total_phy_flow_occ_loss, model
n_mse_flow_occ = n_mse_flow_occ + 1
print ("No_decrease: ", no_decrease)
return total_phy_flow_occ_loss, model
def tensorize(train_vali_test):
result = dict()
result["flow"] = torch.tensor(train_vali_test["flow"])
result["flow_mask"] = torch.tensor(train_vali_test["flow_mask"])
result["occupancy"] = torch.tensor(train_vali_test["occupancy"])
result["occupancy_mask"] = torch.tensor(train_vali_test["occupancy_mask"])
return result
def normalize_flow_occ(tvt, f_o_mean_std): #tvt: train, vali, test
#flow
f_mean, f_std = f_o_mean_std[0], f_o_mean_std[1]
f_mask, f = tvt["flow_mask"], tvt["flow"]
tvt["flow_mask"] = ((np.array(f_mask)-f_mean)/f_std).tolist()
tvt["flow"] = ((np.array(f)-f_mean)/f_std).tolist()
#occ
o_mean, o_std = f_o_mean_std[2], f_o_mean_std[3]
o_mask, o = tvt["occupancy_mask"], tvt["occupancy"]
tvt["occupancy_mask"] = ((np.array(o_mask)-o_mean)/o_std).tolist()
tvt["occupancy"] = ((np.array(o)-o_mean)/o_std).tolist()
return tvt
def transform_distance(d_matrix):
sigma, n_row, n_col = np.std(d_matrix), len(d_matrix), len(d_matrix[0])
sigma_square = sigma*sigma
for i in range(n_row):
for j in range(n_col):
d_i_j = d_matrix[i][j]
d_matrix[i][j] = np.exp(0.0-10000.0*d_i_j*d_i_j/sigma_square)
return d_matrix
def load_data(train_path, vali_path, test_path, sensor_adj_path, mean_std_path, sensor_id_path):
mean_std = json.load(open(mean_std_path))
f_mean, f_std, o_mean, o_std =\
mean_std["f_mean"], mean_std["f_std"], mean_std["o_mean"], mean_std["o_std"]
f_o_mean_std = [f_mean, f_std, o_mean, o_std]
train = json.load(open(train_path))
vali = json.load(open(vali_path))
test = json.load(open(test_path))
adj = json.load(open(sensor_adj_path))["adj"]
n_sensor = len(train["flow"][0])
train = tensorize(normalize_flow_occ(train, f_o_mean_std))
vali = tensorize(normalize_flow_occ(vali, f_o_mean_std))
test = tensorize(normalize_flow_occ(test, f_o_mean_std))
adj = torch.tensor(transform_distance(adj), device=device).float()
df_sensor_id = json.load(open(sensor_id_path))
sensor_length = [0.0 for i in range(n_sensor)]
for sensor in df_sensor_id:
sensor_length[df_sensor_id[sensor][0]] = df_sensor_id[sensor][3]
return train, vali, test, adj, n_sensor, f_o_mean_std, sensor_length
#6.1 load the data
time1 = time.time()
train, vali, test, adj, n_sensor, f_o_mean_std, sensor_length =\
load_data(train_path, vali_path, test_path, sensor_adj_path, mean_std_path, sensor_id_path)
time2 = time.time()
print (time2-time1)
17.001744508743286
print (len(train["flow"]))
print (len(vali["flow"]))
print (len(test["flow"]))
print (f_o_mean_std)
1997 653 653 [241.21586152814126, 220.92336003653475, 0.13805152810287494, 0.1920120065038222]
model = NMFD_GNN(n_sensor, M, hyper_model, f_o_mean_std, sensor_length, adj).to(device)
cri = nn.MSELoss()
#6.2: train the model
total_phy_flow_occ_loss, trained_model = train_process(model, cri, train, vali, test, hyper, f_o_mean_std)
# epochs 200 ----------------an epoch starts------------------- i_epoch: 0 # batch: 124 i_batch: 0.0 the loss for this batch: 1.8325729 flow loss 0.89621675 occ loss 0.82187146 time for this batch 0.6170341968536377 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.6144815 flow loss 0.18863225 occ loss 0.29351518 time for this batch 0.388866662979126 ---------------------------------- train loss for this epoch: 0.739432
time for this epoch 59.01241898536682 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 1 # batch: 124 i_batch: 0.0 the loss for this batch: 0.5885273 flow loss 0.16203003 occ loss 0.2797379 time for this batch 0.33501148223876953 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.6608486 flow loss 0.16983798 occ loss 0.3286397 time for this batch 0.4064362049102783 ---------------------------------- train loss for this epoch: 0.523507
time for this epoch 58.876606702804565 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 2 # batch: 124 i_batch: 0.0 the loss for this batch: 0.40579578 flow loss 0.10739661 occ loss 0.18676661 time for this batch 0.3394155502319336 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.47206962 flow loss 0.11769441 occ loss 0.21992302 time for this batch 0.3991215229034424 ---------------------------------- train loss for this epoch: 0.480317
time for this epoch 58.40217399597168 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 3 # batch: 124 i_batch: 0.0 the loss for this batch: 0.47260636 flow loss 0.108101495 occ loss 0.23388283 time for this batch 0.3452877998352051 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.4711466 flow loss 0.112871625 occ loss 0.24779749 time for this batch 0.39765119552612305 ---------------------------------- train loss for this epoch: 0.461577
time for this epoch 61.901811838150024 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 4 # batch: 124 i_batch: 0.0 the loss for this batch: 0.5227045 flow loss 0.11400799 occ loss 0.26134926 time for this batch 0.36124539375305176 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.43114558 flow loss 0.10096531 occ loss 0.21393514 time for this batch 0.43086886405944824 ---------------------------------- train loss for this epoch: 0.446998
time for this epoch 62.68555212020874 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 5 # batch: 124 i_batch: 0.0 the loss for this batch: 0.46980047 flow loss 0.11033853 occ loss 0.22218437 time for this batch 0.33418726921081543 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.29374596 flow loss 0.07701626 occ loss 0.13169199 time for this batch 0.39302539825439453 ---------------------------------- train loss for this epoch: 0.44038
time for this epoch 65.22787022590637 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 6 # batch: 124 i_batch: 0.0 the loss for this batch: 0.39930427 flow loss 0.104254514 occ loss 0.17226274 time for this batch 0.539492130279541 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.34984085 flow loss 0.0845439 occ loss 0.15992607 time for this batch 0.5715556144714355 ---------------------------------- train loss for this epoch: 0.432499
time for this epoch 85.93762183189392 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 7 # batch: 124 i_batch: 0.0 the loss for this batch: 0.32232672 flow loss 0.08286349 occ loss 0.1614111 time for this batch 0.5128185749053955 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.44597045 flow loss 0.09445828 occ loss 0.21264985 time for this batch 0.5655925273895264 ---------------------------------- train loss for this epoch: 0.427074
time for this epoch 84.52183818817139 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 8 # batch: 124 i_batch: 0.0 the loss for this batch: 0.49011254 flow loss 0.111543305 occ loss 0.23736158 time for this batch 0.5219006538391113 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.3528722 flow loss 0.082674995 occ loss 0.16454522 time for this batch 0.37086963653564453 ---------------------------------- train loss for this epoch: 0.421685
time for this epoch 84.35181403160095 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 9 # batch: 124 i_batch: 0.0 the loss for this batch: 0.5373396 flow loss 0.10806548 occ loss 0.27205122 time for this batch 0.5342507362365723 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.5140677 flow loss 0.10004824 occ loss 0.24890625 time for this batch 0.570458173751831 ---------------------------------- train loss for this epoch: 0.416269
time for this epoch 84.5655164718628 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 10 # batch: 124 i_batch: 0.0 the loss for this batch: 0.32526016 flow loss 0.07304287 occ loss 0.14621791 time for this batch 0.5117051601409912 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.3503657 flow loss 0.07745482 occ loss 0.15763476 time for this batch 0.5650959014892578 ---------------------------------- train loss for this epoch: 0.413319
time for this epoch 84.3258159160614 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 11 # batch: 124 i_batch: 0.0 the loss for this batch: 0.43246758 flow loss 0.09228602 occ loss 0.19742222 time for this batch 0.5242660045623779 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.29098523 flow loss 0.070844136 occ loss 0.12781923 time for this batch 0.5532581806182861 ---------------------------------- train loss for this epoch: 0.408864
time for this epoch 85.17666244506836 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 12 # batch: 124 i_batch: 0.0 the loss for this batch: 0.39346403 flow loss 0.09602988 occ loss 0.17933083 time for this batch 0.5022192001342773 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.500859 flow loss 0.1068501 occ loss 0.23778689 time for this batch 0.5596976280212402 ---------------------------------- train loss for this epoch: 0.406306
time for this epoch 84.55423760414124 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 13 # batch: 124 i_batch: 0.0 the loss for this batch: 0.3682206 flow loss 0.100955814 occ loss 0.15884253 time for this batch 0.47971510887145996 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.45847112 flow loss 0.09882657 occ loss 0.21572395 time for this batch 0.5571267604827881 ---------------------------------- train loss for this epoch: 0.404031
time for this epoch 83.81766867637634 No_decrease: 3 ----------------an epoch starts------------------- i_epoch: 14 # batch: 124 i_batch: 0.0 the loss for this batch: 0.44410497 flow loss 0.10140443 occ loss 0.20388505 time for this batch 0.5098800659179688 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.4862147 flow loss 0.10731892 occ loss 0.23490888 time for this batch 0.45563483238220215 ---------------------------------- train loss for this epoch: 0.399447
time for this epoch 86.1754002571106 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 15 # batch: 124 i_batch: 0.0 the loss for this batch: 0.44450736 flow loss 0.09572962 occ loss 0.21095005 time for this batch 0.5807864665985107 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.41661286 flow loss 0.10194375 occ loss 0.18980454 time for this batch 0.586920976638794 ---------------------------------- train loss for this epoch: 0.39893
time for this epoch 86.47107100486755 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 16 # batch: 124 i_batch: 0.0 the loss for this batch: 0.42428005 flow loss 0.0932424 occ loss 0.19155395 time for this batch 0.5133030414581299 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.34306848 flow loss 0.08060854 occ loss 0.15214866 time for this batch 0.5533773899078369 ---------------------------------- train loss for this epoch: 0.396668
time for this epoch 84.16269207000732 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 17 # batch: 124 i_batch: 0.0 the loss for this batch: 0.3181974 flow loss 0.07676232 occ loss 0.1414236 time for this batch 0.41672539710998535 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.34888884 flow loss 0.07222549 occ loss 0.16495839 time for this batch 0.5787758827209473 ---------------------------------- train loss for this epoch: 0.394122
time for this epoch 84.96643877029419 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 18 # batch: 124 i_batch: 0.0 the loss for this batch: 0.41504002 flow loss 0.08770894 occ loss 0.18664671 time for this batch 0.4809439182281494 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.35824844 flow loss 0.082396224 occ loss 0.15827265 time for this batch 0.5580668449401855 ---------------------------------- train loss for this epoch: 0.393409
time for this epoch 84.41791844367981 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 19 # batch: 124 i_batch: 0.0 the loss for this batch: 0.31489667 flow loss 0.07089513 occ loss 0.15039134 time for this batch 0.5127110481262207 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.35490188 flow loss 0.08206008 occ loss 0.17251581 time for this batch 0.4067728519439697 ---------------------------------- train loss for this epoch: 0.392643
time for this epoch 84.15514397621155 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 20 # batch: 124 i_batch: 0.0 the loss for this batch: 0.3894797 flow loss 0.07821989 occ loss 0.19263938 time for this batch 0.3826901912689209 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.33755466 flow loss 0.075437605 occ loss 0.15494226 time for this batch 0.5490522384643555 ---------------------------------- train loss for this epoch: 0.390418
time for this epoch 83.51794743537903 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 21 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2579735 flow loss 0.06574297 occ loss 0.10903427 time for this batch 0.4808681011199951 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.43986455 flow loss 0.101587415 occ loss 0.20239575 time for this batch 0.5549705028533936 ---------------------------------- train loss for this epoch: 0.38925
time for this epoch 82.84142088890076 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 22 # batch: 124 i_batch: 0.0 the loss for this batch: 0.51861 flow loss 0.112932414 occ loss 0.2591961 time for this batch 0.4987154006958008 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.4753052 flow loss 0.10329475 occ loss 0.21647339 time for this batch 0.5435469150543213 ---------------------------------- train loss for this epoch: 0.388856
time for this epoch 83.77294683456421 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 23 # batch: 124 i_batch: 0.0 the loss for this batch: 0.4199681 flow loss 0.08401766 occ loss 0.1943481 time for this batch 0.47499608993530273 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.33947644 flow loss 0.071929455 occ loss 0.1471746 time for this batch 0.39894986152648926 ---------------------------------- train loss for this epoch: 0.386442
time for this epoch 82.44995784759521 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 24 # batch: 124 i_batch: 0.0 the loss for this batch: 0.39408126 flow loss 0.091057554 occ loss 0.175594 time for this batch 0.5125844478607178 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.3134563 flow loss 0.07840421 occ loss 0.1369148 time for this batch 0.5084109306335449 ---------------------------------- train loss for this epoch: 0.385294
time for this epoch 83.78894543647766 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 25 # batch: 124 i_batch: 0.0 the loss for this batch: 0.3678293 flow loss 0.081824124 occ loss 0.17140347 time for this batch 0.5250282287597656 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.3917352 flow loss 0.08160328 occ loss 0.19489354 time for this batch 0.5664491653442383 ---------------------------------- train loss for this epoch: 0.38407
time for this epoch 84.4245126247406 No_decrease: 3 ----------------an epoch starts------------------- i_epoch: 26 # batch: 124 i_batch: 0.0 the loss for this batch: 0.5716673 flow loss 0.11565768 occ loss 0.27165332 time for this batch 0.48095226287841797 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.47119576 flow loss 0.10373575 occ loss 0.2170749 time for this batch 0.5616791248321533 ---------------------------------- train loss for this epoch: 0.384619
time for this epoch 83.25258421897888 No_decrease: 4 ----------------an epoch starts------------------- i_epoch: 27 # batch: 124 i_batch: 0.0 the loss for this batch: 0.3162808 flow loss 0.0699872 occ loss 0.15703647 time for this batch 0.4985816478729248 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.42911828 flow loss 0.0930712 occ loss 0.19705509 time for this batch 0.5679404735565186 ---------------------------------- train loss for this epoch: 0.383635
time for this epoch 83.23864364624023 No_decrease: 5 ----------------an epoch starts------------------- i_epoch: 28 # batch: 124 i_batch: 0.0 the loss for this batch: 0.38434437 flow loss 0.09029838 occ loss 0.17182669 time for this batch 0.5349509716033936 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.3899114 flow loss 0.08707689 occ loss 0.17943142 time for this batch 0.5657718181610107 ---------------------------------- train loss for this epoch: 0.381834
time for this epoch 83.4757649898529 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 29 # batch: 124 i_batch: 0.0 the loss for this batch: 0.36776114 flow loss 0.07628368 occ loss 0.1628206 time for this batch 0.5165677070617676 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.5190271 flow loss 0.10248567 occ loss 0.24143887 time for this batch 0.5729541778564453 ---------------------------------- train loss for this epoch: 0.381462
time for this epoch 84.22597455978394 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 30 # batch: 124 i_batch: 0.0 the loss for this batch: 0.51092005 flow loss 0.10538039 occ loss 0.2334836 time for this batch 0.49190521240234375 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.44246995 flow loss 0.08554385 occ loss 0.19705969 time for this batch 0.5325868129730225 ---------------------------------- train loss for this epoch: 0.382628
time for this epoch 84.55201411247253 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 31 # batch: 124 i_batch: 0.0 the loss for this batch: 0.48814407 flow loss 0.09609854 occ loss 0.22412731 time for this batch 0.33892202377319336 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.4033553 flow loss 0.07840918 occ loss 0.1887489 time for this batch 0.5500345230102539 ---------------------------------- train loss for this epoch: 0.379548
time for this epoch 83.25360655784607 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 32 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2933299 flow loss 0.063253365 occ loss 0.14578676 time for this batch 0.47564053535461426 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.3569315 flow loss 0.0796314 occ loss 0.15727688 time for this batch 0.567439079284668 ---------------------------------- train loss for this epoch: 0.377805
time for this epoch 84.28117275238037 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 33 # batch: 124 i_batch: 0.0 the loss for this batch: 0.3852728 flow loss 0.0824926 occ loss 0.175282 time for this batch 0.5156998634338379 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.3363636 flow loss 0.07496626 occ loss 0.1566548 time for this batch 0.5368843078613281 ---------------------------------- train loss for this epoch: 0.375043
time for this epoch 84.54397678375244 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 34 # batch: 124 i_batch: 0.0 the loss for this batch: 0.40059084 flow loss 0.09630689 occ loss 0.18995029 time for this batch 0.507075309753418 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.39627603 flow loss 0.08729494 occ loss 0.18147966 time for this batch 0.5647118091583252 ---------------------------------- train loss for this epoch: 0.373895
time for this epoch 84.09545016288757 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 35 # batch: 124 i_batch: 0.0 the loss for this batch: 0.4362095 flow loss 0.09327476 occ loss 0.19519357 time for this batch 0.503746509552002 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.34782556 flow loss 0.08128125 occ loss 0.15613922 time for this batch 0.6411550045013428 ---------------------------------- train loss for this epoch: 0.366385
time for this epoch 83.97909331321716 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 36 # batch: 124 i_batch: 0.0 the loss for this batch: 0.35377902 flow loss 0.074001566 occ loss 0.1737738 time for this batch 0.5049054622650146 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.3638198 flow loss 0.08899392 occ loss 0.17047034 time for this batch 0.5478289127349854 ---------------------------------- train loss for this epoch: 0.35537
time for this epoch 84.82249665260315 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 37 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2717862 flow loss 0.06241016 occ loss 0.1281517 time for this batch 0.4116847515106201 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.30370462 flow loss 0.072770216 occ loss 0.1512541 time for this batch 0.553152322769165 ---------------------------------- train loss for this epoch: 0.33947
time for this epoch 83.41134905815125 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 38 # batch: 124 i_batch: 0.0 the loss for this batch: 0.45990765 flow loss 0.110276595 occ loss 0.24727742 time for this batch 0.4936387538909912 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.3960239 flow loss 0.08552338 occ loss 0.21235473 time for this batch 0.5649080276489258 ---------------------------------- train loss for this epoch: 0.317821
time for this epoch 85.34671521186829 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 39 # batch: 124 i_batch: 0.0 the loss for this batch: 0.3279369 flow loss 0.075558096 occ loss 0.1817833 time for this batch 0.3581991195678711 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.4023878 flow loss 0.09011148 occ loss 0.24514672 time for this batch 0.5606174468994141 ---------------------------------- train loss for this epoch: 0.294768
time for this epoch 85.07291555404663 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 40 # batch: 124 i_batch: 0.0 the loss for this batch: 0.31489816 flow loss 0.08561872 occ loss 0.18720895 time for this batch 0.4771435260772705 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.20005436 flow loss 0.054871947 occ loss 0.121733874 time for this batch 0.5756595134735107 ---------------------------------- train loss for this epoch: 0.270046
time for this epoch 87.92265939712524 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 41 # batch: 124 i_batch: 0.0 the loss for this batch: 0.22996388 flow loss 0.061454426 occ loss 0.15236445 time for this batch 0.48435378074645996 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.23080909 flow loss 0.06345322 occ loss 0.15331171 time for this batch 0.568213701248169 ---------------------------------- train loss for this epoch: 0.249163
time for this epoch 85.31990790367126 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 42 # batch: 124 i_batch: 0.0 the loss for this batch: 0.19678243 flow loss 0.053055037 occ loss 0.13638891 time for this batch 0.4614284038543701 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2730554 flow loss 0.069754176 occ loss 0.19762605 time for this batch 0.576434850692749 ---------------------------------- train loss for this epoch: 0.238929
time for this epoch 83.56304287910461 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 43 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2485679 flow loss 0.07258584 occ loss 0.1732784 time for this batch 0.46524858474731445 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.33229578 flow loss 0.08634651 occ loss 0.2438268 time for this batch 0.5537283420562744 ---------------------------------- train loss for this epoch: 0.233794
time for this epoch 84.98172879219055 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 44 # batch: 124 i_batch: 0.0 the loss for this batch: 0.19438767 flow loss 0.061165266 occ loss 0.1322545 time for this batch 0.49664306640625 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2545915 flow loss 0.06776179 occ loss 0.18571256 time for this batch 0.55104660987854 ---------------------------------- train loss for this epoch: 0.232738
time for this epoch 85.01822066307068 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 45 # batch: 124 i_batch: 0.0 the loss for this batch: 0.32003617 flow loss 0.07729222 occ loss 0.24185947 time for this batch 0.35245275497436523 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.19148402 flow loss 0.052372742 occ loss 0.1384043 time for this batch 0.5287127494812012 ---------------------------------- train loss for this epoch: 0.231701
time for this epoch 83.52418160438538 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 46 # batch: 124 i_batch: 0.0 the loss for this batch: 0.22095464 flow loss 0.062012207 occ loss 0.15849857 time for this batch 0.5171504020690918 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.22482507 flow loss 0.061277367 occ loss 0.16303338 time for this batch 0.5722324848175049 ---------------------------------- train loss for this epoch: 0.231816
time for this epoch 85.73759365081787 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 47 # batch: 124 i_batch: 0.0 the loss for this batch: 0.19347773 flow loss 0.054576717 occ loss 0.13829875 time for this batch 0.5326368808746338 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.20425886 flow loss 0.06163582 occ loss 0.14169873 time for this batch 0.5738112926483154 ---------------------------------- train loss for this epoch: 0.232196
time for this epoch 82.97716498374939 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 48 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20287435 flow loss 0.05837168 occ loss 0.1440246 time for this batch 0.49195075035095215 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.26370102 flow loss 0.06942228 occ loss 0.19380766 time for this batch 0.5384156703948975 ---------------------------------- train loss for this epoch: 0.229297
time for this epoch 84.13713479042053 No_decrease: 3 ----------------an epoch starts------------------- i_epoch: 49 # batch: 124 i_batch: 0.0 the loss for this batch: 0.24488224 flow loss 0.066502795 occ loss 0.1776626 time for this batch 0.4844374656677246 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.24603571 flow loss 0.069106765 occ loss 0.17635241 time for this batch 0.5628104209899902 ---------------------------------- train loss for this epoch: 0.230441
time for this epoch 84.25959134101868 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 50 # batch: 124 i_batch: 0.0 the loss for this batch: 0.29809016 flow loss 0.07260583 occ loss 0.22488959 time for this batch 0.5253608226776123 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.31168753 flow loss 0.07345627 occ loss 0.23765741 time for this batch 0.5810210704803467 ---------------------------------- train loss for this epoch: 0.229593
time for this epoch 84.30539131164551 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 51 # batch: 124 i_batch: 0.0 the loss for this batch: 0.22591785 flow loss 0.06705319 occ loss 0.15846011 time for this batch 0.4254636764526367 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.28221527 flow loss 0.07548429 occ loss 0.20627482 time for this batch 0.5579097270965576 ---------------------------------- train loss for this epoch: 0.227954
time for this epoch 83.51873421669006 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 52 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20371328 flow loss 0.05557267 occ loss 0.14776838 time for this batch 0.5053398609161377 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.14228614 flow loss 0.046353057 occ loss 0.095618926 time for this batch 0.548720121383667 ---------------------------------- train loss for this epoch: 0.227232
time for this epoch 83.99161028862 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 53 # batch: 124 i_batch: 0.0 the loss for this batch: 0.24266607 flow loss 0.062794745 occ loss 0.1794445 time for this batch 0.5113322734832764 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.24234538 flow loss 0.063731514 occ loss 0.1779572 time for this batch 0.5639169216156006 ---------------------------------- train loss for this epoch: 0.227456
time for this epoch 83.66939616203308 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 54 # batch: 124 i_batch: 0.0 the loss for this batch: 0.23562923 flow loss 0.06350872 occ loss 0.1713962 time for this batch 0.4445936679840088 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.16878253 flow loss 0.05182514 occ loss 0.116238326 time for this batch 0.5180585384368896 ---------------------------------- train loss for this epoch: 0.228002
time for this epoch 82.69022464752197 No_decrease: 3 ----------------an epoch starts------------------- i_epoch: 55 # batch: 124 i_batch: 0.0 the loss for this batch: 0.24194439 flow loss 0.06149433 occ loss 0.18000442 time for this batch 0.4951012134552002 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2099241 flow loss 0.055741545 occ loss 0.15328671 time for this batch 0.5753951072692871 ---------------------------------- train loss for this epoch: 0.227324
time for this epoch 85.69332313537598 No_decrease: 4 ----------------an epoch starts------------------- i_epoch: 56 # batch: 124 i_batch: 0.0 the loss for this batch: 0.24684736 flow loss 0.064126045 occ loss 0.18240279 time for this batch 0.5245950222015381 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.29252824 flow loss 0.07480028 occ loss 0.21710427 time for this batch 0.5582888126373291 ---------------------------------- train loss for this epoch: 0.22757
time for this epoch 83.75726699829102 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 57 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2244146 flow loss 0.061590433 occ loss 0.16236547 time for this batch 0.46871280670166016 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.17647523 flow loss 0.050862443 occ loss 0.12519999 time for this batch 0.5159375667572021 ---------------------------------- train loss for this epoch: 0.226626
time for this epoch 83.30871868133545 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 58 # batch: 124 i_batch: 0.0 the loss for this batch: 0.18432926 flow loss 0.052428693 occ loss 0.13126166 time for this batch 0.48993515968322754 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2521375 flow loss 0.06600719 occ loss 0.1851895 time for this batch 0.5611279010772705 ---------------------------------- train loss for this epoch: 0.22697
time for this epoch 84.04945015907288 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 59 # batch: 124 i_batch: 0.0 the loss for this batch: 0.17502739 flow loss 0.05348824 occ loss 0.121165596 time for this batch 0.5169558525085449 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2283923 flow loss 0.06031867 occ loss 0.16707936 time for this batch 0.5610418319702148 ---------------------------------- train loss for this epoch: 0.225742
time for this epoch 83.71819829940796 No_decrease: 3 ----------------an epoch starts------------------- i_epoch: 60 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2612831 flow loss 0.06844395 occ loss 0.19236594 time for this batch 0.5125010013580322 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.22618423 flow loss 0.06022175 occ loss 0.16525392 time for this batch 0.5704493522644043 ---------------------------------- train loss for this epoch: 0.224925
time for this epoch 84.75423264503479 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 61 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20907754 flow loss 0.06040661 occ loss 0.14803141 time for this batch 0.5010745525360107 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.16686653 flow loss 0.046193667 occ loss 0.11961773 time for this batch 0.573613166809082 ---------------------------------- train loss for this epoch: 0.228046
time for this epoch 87.14471745491028 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 62 # batch: 124 i_batch: 0.0 the loss for this batch: 0.15058775 flow loss 0.048304014 occ loss 0.10188859 time for this batch 0.49124789237976074 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.25970793 flow loss 0.0677334 occ loss 0.19068411 time for this batch 0.5468811988830566 ---------------------------------- train loss for this epoch: 0.224923
time for this epoch 84.79379606246948 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 63 # batch: 124 i_batch: 0.0 the loss for this batch: 0.238081 flow loss 0.068138726 occ loss 0.16941439 time for this batch 0.4865896701812744 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.20004247 flow loss 0.052348297 occ loss 0.14729318 time for this batch 0.43762898445129395 ---------------------------------- train loss for this epoch: 0.224857
time for this epoch 83.92381358146667 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 64 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2232662 flow loss 0.060374595 occ loss 0.16224086 time for this batch 0.4583771228790283 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.22585294 flow loss 0.0593941 occ loss 0.16591382 time for this batch 0.524878978729248 ---------------------------------- train loss for this epoch: 0.226221
time for this epoch 83.49435949325562 No_decrease: 3 ----------------an epoch starts------------------- i_epoch: 65 # batch: 124 i_batch: 0.0 the loss for this batch: 0.1997342 flow loss 0.056873366 occ loss 0.14241442 time for this batch 0.4558401107788086 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.09245802 flow loss 0.030407967 occ loss 0.06093147 time for this batch 0.5301706790924072 ---------------------------------- train loss for this epoch: 0.22364
time for this epoch 84.71480083465576 No_decrease: 4 ----------------an epoch starts------------------- i_epoch: 66 # batch: 124 i_batch: 0.0 the loss for this batch: 0.23523402 flow loss 0.06540971 occ loss 0.16892712 time for this batch 0.5254650115966797 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.248395 flow loss 0.06461511 occ loss 0.18341507 time for this batch 0.5514125823974609 ---------------------------------- train loss for this epoch: 0.223201
time for this epoch 83.52707767486572 No_decrease: 5 ----------------an epoch starts------------------- i_epoch: 67 # batch: 124 i_batch: 0.0 the loss for this batch: 0.23560447 flow loss 0.06596967 occ loss 0.16931356 time for this batch 0.4893653392791748 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.21563745 flow loss 0.05808709 occ loss 0.15658374 time for this batch 0.5511577129364014 ---------------------------------- train loss for this epoch: 0.223417
time for this epoch 84.43798851966858 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 68 # batch: 124 i_batch: 0.0 the loss for this batch: 0.17057884 flow loss 0.05071873 occ loss 0.11947536 time for this batch 0.46851134300231934 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.17558567 flow loss 0.047760386 occ loss 0.1274634 time for this batch 0.5859391689300537 ---------------------------------- train loss for this epoch: 0.222085
time for this epoch 84.00654625892639 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 69 # batch: 124 i_batch: 0.0 the loss for this batch: 0.24068995 flow loss 0.062557764 occ loss 0.17756632 time for this batch 0.4371509552001953 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.24063921 flow loss 0.06901637 occ loss 0.17110391 time for this batch 0.5536627769470215 ---------------------------------- train loss for this epoch: 0.222571
time for this epoch 84.74192643165588 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 70 # batch: 124 i_batch: 0.0 the loss for this batch: 0.21558739 flow loss 0.052905805 occ loss 0.1622738 time for this batch 0.4119997024536133 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.1985156 flow loss 0.053922687 occ loss 0.14421457 time for this batch 0.4918816089630127 ---------------------------------- train loss for this epoch: 0.222036
time for this epoch 81.00452303886414 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 71 # batch: 124 i_batch: 0.0 the loss for this batch: 0.23449889 flow loss 0.062810846 occ loss 0.17128077 time for this batch 0.5333771705627441 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.19955376 flow loss 0.05593946 occ loss 0.14325032 time for this batch 0.5648207664489746 ---------------------------------- train loss for this epoch: 0.222989
time for this epoch 83.04286789894104 No_decrease: 3 ----------------an epoch starts------------------- i_epoch: 72 # batch: 124 i_batch: 0.0 the loss for this batch: 0.25260004 flow loss 0.06339055 occ loss 0.18857889 time for this batch 0.5188643932342529 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2590625 flow loss 0.06494599 occ loss 0.19361646 time for this batch 0.542374849319458 ---------------------------------- train loss for this epoch: 0.221685
time for this epoch 84.28779244422913 No_decrease: 4 ----------------an epoch starts------------------- i_epoch: 73 # batch: 124 i_batch: 0.0 the loss for this batch: 0.18239285 flow loss 0.04898853 occ loss 0.13250402 time for this batch 0.4933161735534668 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2614807 flow loss 0.07136423 occ loss 0.18952101 time for this batch 0.5702300071716309 ---------------------------------- train loss for this epoch: 0.222428
time for this epoch 85.03833436965942 No_decrease: 5 ----------------an epoch starts------------------- i_epoch: 74 # batch: 124 i_batch: 0.0 the loss for this batch: 0.22898993 flow loss 0.064025156 occ loss 0.16464588 time for this batch 0.3907203674316406 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2089675 flow loss 0.056500148 occ loss 0.15201274 time for this batch 0.5719122886657715 ---------------------------------- train loss for this epoch: 0.222907
time for this epoch 83.37429141998291 No_decrease: 6 ----------------an epoch starts------------------- i_epoch: 75 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2456042 flow loss 0.06446991 occ loss 0.18074094 time for this batch 0.4796111583709717 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2383991 flow loss 0.06359564 occ loss 0.1742942 time for this batch 0.5413017272949219 ---------------------------------- train loss for this epoch: 0.222221
time for this epoch 84.2179205417633 No_decrease: 7 ----------------an epoch starts------------------- i_epoch: 76 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2569832 flow loss 0.06355791 occ loss 0.19229193 time for this batch 0.5133883953094482 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.25156468 flow loss 0.06539758 occ loss 0.18576925 time for this batch 0.5559184551239014 ---------------------------------- train loss for this epoch: 0.221677
time for this epoch 85.45092391967773 No_decrease: 8 ----------------an epoch starts------------------- i_epoch: 77 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2563657 flow loss 0.06912639 occ loss 0.18671554 time for this batch 0.5051229000091553 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.23010844 flow loss 0.0646355 occ loss 0.1650719 time for this batch 0.5682172775268555 ---------------------------------- train loss for this epoch: 0.219998
time for this epoch 83.61398673057556 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 78 # batch: 124 i_batch: 0.0 the loss for this batch: 0.21131738 flow loss 0.05737553 occ loss 0.1536279 time for this batch 0.5171430110931396 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2099907 flow loss 0.059243385 occ loss 0.15040497 time for this batch 0.5562155246734619 ---------------------------------- train loss for this epoch: 0.219755
time for this epoch 83.42787790298462 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 79 # batch: 124 i_batch: 0.0 the loss for this batch: 0.24913286 flow loss 0.062082376 occ loss 0.18661289 time for this batch 0.5053348541259766 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.21534455 flow loss 0.05823717 occ loss 0.1566792 time for this batch 0.5463688373565674 ---------------------------------- train loss for this epoch: 0.219667
time for this epoch 82.60279655456543 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 80 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2235837 flow loss 0.0624936 occ loss 0.16070282 time for this batch 0.5041463375091553 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.26113924 flow loss 0.06760566 occ loss 0.19295248 time for this batch 0.5641059875488281 ---------------------------------- train loss for this epoch: 0.220784
time for this epoch 83.0617995262146 No_decrease: 3 ----------------an epoch starts------------------- i_epoch: 81 # batch: 124 i_batch: 0.0 the loss for this batch: 0.194152 flow loss 0.058472615 occ loss 0.13456748 time for this batch 0.5097784996032715 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.13963069 flow loss 0.044537414 occ loss 0.09487984 time for this batch 0.5528428554534912 ---------------------------------- train loss for this epoch: 0.220671
time for this epoch 84.13176727294922 No_decrease: 4 ----------------an epoch starts------------------- i_epoch: 82 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2493163 flow loss 0.06279669 occ loss 0.18591711 time for this batch 0.48450350761413574 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.20866852 flow loss 0.0594654 occ loss 0.14854684 time for this batch 0.5426416397094727 ---------------------------------- train loss for this epoch: 0.220739
time for this epoch 75.91315221786499 No_decrease: 5 ----------------an epoch starts------------------- i_epoch: 83 # batch: 124 i_batch: 0.0 the loss for this batch: 0.25970268 flow loss 0.0709593 occ loss 0.18797287 time for this batch 0.3966512680053711 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.25711325 flow loss 0.064098544 occ loss 0.19218262 time for this batch 0.37326884269714355 ---------------------------------- train loss for this epoch: 0.21967
time for this epoch 58.28587555885315 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 84 # batch: 124 i_batch: 0.0 the loss for this batch: 0.17332663 flow loss 0.048310272 occ loss 0.124510884 time for this batch 0.3415234088897705 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.1655101 flow loss 0.048248112 occ loss 0.116654746 time for this batch 0.4513218402862549 ---------------------------------- train loss for this epoch: 0.218242
time for this epoch 63.807405948638916 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 85 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2115246 flow loss 0.05801209 occ loss 0.15294796 time for this batch 0.3828566074371338 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2159254 flow loss 0.05469317 occ loss 0.16069154 time for this batch 0.41068220138549805 ---------------------------------- train loss for this epoch: 0.219016
time for this epoch 66.1804871559143 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 86 # batch: 124 i_batch: 0.0 the loss for this batch: 0.25585258 flow loss 0.06320879 occ loss 0.19217889 time for this batch 0.34677839279174805 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.1438767 flow loss 0.04478986 occ loss 0.09867533 time for this batch 0.40975093841552734 ---------------------------------- train loss for this epoch: 0.219002
time for this epoch 64.44793891906738 No_decrease: 3 ----------------an epoch starts------------------- i_epoch: 87 # batch: 124 i_batch: 0.0 the loss for this batch: 0.27005622 flow loss 0.06624788 occ loss 0.20329665 time for this batch 0.33176326751708984 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.17852001 flow loss 0.05324008 occ loss 0.1241627 time for this batch 0.4304773807525635 ---------------------------------- train loss for this epoch: 0.218535
time for this epoch 66.7626793384552 No_decrease: 4 ----------------an epoch starts------------------- i_epoch: 88 # batch: 124 i_batch: 0.0 the loss for this batch: 0.24100548 flow loss 0.064057216 occ loss 0.17623314 time for this batch 0.3731048107147217 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.27682722 flow loss 0.065135844 occ loss 0.2111589 time for this batch 0.4143791198730469 ---------------------------------- train loss for this epoch: 0.217886
time for this epoch 65.19604277610779 No_decrease: 5 ----------------an epoch starts------------------- i_epoch: 89 # batch: 124 i_batch: 0.0 the loss for this batch: 0.24924393 flow loss 0.06535388 occ loss 0.18331547 time for this batch 0.37300992012023926 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.17869867 flow loss 0.049315237 occ loss 0.12912256 time for this batch 0.42612338066101074 ---------------------------------- train loss for this epoch: 0.217505
time for this epoch 63.732266426086426 No_decrease: 6 ----------------an epoch starts------------------- i_epoch: 90 # batch: 124 i_batch: 0.0 the loss for this batch: 0.23564234 flow loss 0.06574176 occ loss 0.16917528 time for this batch 0.3598670959472656 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.16738579 flow loss 0.049109958 occ loss 0.11710283 time for this batch 0.4193565845489502 ---------------------------------- train loss for this epoch: 0.218323
time for this epoch 64.63648843765259 No_decrease: 7 ----------------an epoch starts------------------- i_epoch: 91 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2488573 flow loss 0.064949535 occ loss 0.18313944 time for this batch 0.3610410690307617 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.25940475 flow loss 0.06806622 occ loss 0.19076364 time for this batch 0.3874030113220215 ---------------------------------- train loss for this epoch: 0.217404
time for this epoch 64.59205412864685 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 92 # batch: 124 i_batch: 0.0 the loss for this batch: 0.24365667 flow loss 0.06323199 occ loss 0.17991407 time for this batch 0.3637123107910156 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2591096 flow loss 0.06719441 occ loss 0.19143182 time for this batch 0.384566068649292 ---------------------------------- train loss for this epoch: 0.218281
time for this epoch 63.81357216835022 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 93 # batch: 124 i_batch: 0.0 the loss for this batch: 0.15030858 flow loss 0.04397252 occ loss 0.10608012 time for this batch 0.3642585277557373 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.23949549 flow loss 0.06476616 occ loss 0.17441328 time for this batch 0.39472031593322754 ---------------------------------- train loss for this epoch: 0.217241
time for this epoch 68.19953441619873 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 94 # batch: 124 i_batch: 0.0 the loss for this batch: 0.21005936 flow loss 0.057000864 occ loss 0.1527069 time for this batch 0.38373541831970215 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.24292865 flow loss 0.06774516 occ loss 0.17455712 time for this batch 0.34375929832458496 ---------------------------------- train loss for this epoch: 0.217591
time for this epoch 66.58888030052185 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 95 # batch: 124 i_batch: 0.0 the loss for this batch: 0.19783774 flow loss 0.05321843 occ loss 0.14421703 time for this batch 0.40873241424560547 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.25196713 flow loss 0.06693157 occ loss 0.18446991 time for this batch 0.44325995445251465 ---------------------------------- train loss for this epoch: 0.217034
time for this epoch 65.32320761680603 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 96 # batch: 124 i_batch: 0.0 the loss for this batch: 0.24571352 flow loss 0.062460724 occ loss 0.18286 time for this batch 0.3608896732330322 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.18070544 flow loss 0.048841663 occ loss 0.13109758 time for this batch 0.45134902000427246 ---------------------------------- train loss for this epoch: 0.216379
time for this epoch 64.73498463630676 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 97 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20019133 flow loss 0.054410268 occ loss 0.1455003 time for this batch 0.38420939445495605 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.23888063 flow loss 0.060537193 occ loss 0.17778254 time for this batch 0.41312289237976074 ---------------------------------- train loss for this epoch: 0.217333
time for this epoch 63.846593618392944 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 98 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2380092 flow loss 0.06025679 occ loss 0.17718326 time for this batch 0.34903812408447266 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.14318986 flow loss 0.043290667 occ loss 0.09931365 time for this batch 0.42720746994018555 ---------------------------------- train loss for this epoch: 0.217417
time for this epoch 64.64035844802856 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 99 # batch: 124 i_batch: 0.0 the loss for this batch: 0.29479352 flow loss 0.07242925 occ loss 0.22174795 time for this batch 0.3403284549713135 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.17862475 flow loss 0.0483349 occ loss 0.12943485 time for this batch 0.44529199600219727 ---------------------------------- train loss for this epoch: 0.216041
time for this epoch 64.39432716369629 No_decrease: 3 ----------------an epoch starts------------------- i_epoch: 100 # batch: 124 i_batch: 0.0 the loss for this batch: 0.21573491 flow loss 0.056198645 occ loss 0.15868136 time for this batch 0.39453983306884766 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2574591 flow loss 0.06382943 occ loss 0.1931539 time for this batch 0.40993762016296387 ---------------------------------- train loss for this epoch: 0.214767
time for this epoch 64.8930995464325 No_decrease: 4 ----------------an epoch starts------------------- i_epoch: 101 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2134245 flow loss 0.05830187 occ loss 0.15487315 time for this batch 0.3812541961669922 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.21218203 flow loss 0.060551092 occ loss 0.15134591 time for this batch 0.42412424087524414 ---------------------------------- train loss for this epoch: 0.216757
time for this epoch 67.26193261146545 No_decrease: 5 ----------------an epoch starts------------------- i_epoch: 102 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2045396 flow loss 0.054200795 occ loss 0.14982021 time for this batch 0.3498053550720215 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.26640293 flow loss 0.07267667 occ loss 0.19323249 time for this batch 0.42275047302246094 ---------------------------------- train loss for this epoch: 0.216787
time for this epoch 62.971516132354736 No_decrease: 6 ----------------an epoch starts------------------- i_epoch: 103 # batch: 124 i_batch: 0.0 the loss for this batch: 0.16169177 flow loss 0.0464283 occ loss 0.11476285 time for this batch 0.36420679092407227 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.22479574 flow loss 0.057799358 occ loss 0.16623107 time for this batch 0.42071533203125 ---------------------------------- train loss for this epoch: 0.215182
time for this epoch 65.72509837150574 No_decrease: 7 ----------------an epoch starts------------------- i_epoch: 104 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20773292 flow loss 0.05433523 occ loss 0.15295874 time for this batch 0.2949657440185547 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.17399718 flow loss 0.047477346 occ loss 0.12622824 time for this batch 0.45902514457702637 ---------------------------------- train loss for this epoch: 0.213683
time for this epoch 62.31619310379028 No_decrease: 8 ----------------an epoch starts------------------- i_epoch: 105 # batch: 124 i_batch: 0.0 the loss for this batch: 0.238103 flow loss 0.062256362 occ loss 0.17537323 time for this batch 0.33134961128234863 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.15134357 flow loss 0.047013268 occ loss 0.103873245 time for this batch 0.26640963554382324 ---------------------------------- train loss for this epoch: 0.214808
time for this epoch 57.200127363204956 No_decrease: 9 ----------------an epoch starts------------------- i_epoch: 106 # batch: 124 i_batch: 0.0 the loss for this batch: 0.16489641 flow loss 0.04617712 occ loss 0.11798085 time for this batch 0.31870484352111816 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.21705592 flow loss 0.062380318 occ loss 0.15413512 time for this batch 0.26209330558776855 ---------------------------------- train loss for this epoch: 0.214462
time for this epoch 41.14203596115112 No_decrease: 10 ----------------an epoch starts------------------- i_epoch: 107 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20263122 flow loss 0.05597266 occ loss 0.14578895 time for this batch 0.2600419521331787 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.19281527 flow loss 0.05420233 occ loss 0.1383101 time for this batch 0.25994420051574707 ---------------------------------- train loss for this epoch: 0.214594
time for this epoch 41.659284830093384 No_decrease: 11 ----------------an epoch starts------------------- i_epoch: 108 # batch: 124 i_batch: 0.0 the loss for this batch: 0.24151935 flow loss 0.064832576 occ loss 0.17629452 time for this batch 0.3309924602508545 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.17401674 flow loss 0.049683288 occ loss 0.12394314 time for this batch 0.3965325355529785 ---------------------------------- train loss for this epoch: 0.215671
time for this epoch 58.20651292800903 No_decrease: 12 ----------------an epoch starts------------------- i_epoch: 109 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20750462 flow loss 0.05636002 occ loss 0.15053153 time for this batch 0.3348660469055176 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.29331374 flow loss 0.07312722 occ loss 0.21965334 time for this batch 0.4055168628692627 ---------------------------------- train loss for this epoch: 0.214796
time for this epoch 56.8858642578125 No_decrease: 13 ----------------an epoch starts------------------- i_epoch: 110 # batch: 124 i_batch: 0.0 the loss for this batch: 0.27448687 flow loss 0.06854689 occ loss 0.20544122 time for this batch 0.3478577136993408 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2272467 flow loss 0.059201792 occ loss 0.16742916 time for this batch 0.3696908950805664 ---------------------------------- train loss for this epoch: 0.213343
time for this epoch 58.97466039657593 No_decrease: 14 ----------------an epoch starts------------------- i_epoch: 111 # batch: 124 i_batch: 0.0 the loss for this batch: 0.18690006 flow loss 0.050605986 occ loss 0.13583183 time for this batch 0.32954835891723633 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.20575587 flow loss 0.057697132 occ loss 0.14765014 time for this batch 0.33835363388061523 ---------------------------------- train loss for this epoch: 0.216044
time for this epoch 58.714296102523804 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 112 # batch: 124 i_batch: 0.0 the loss for this batch: 0.14111437 flow loss 0.037440326 occ loss 0.103454225 time for this batch 0.31122541427612305 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.22837189 flow loss 0.059179734 occ loss 0.16875184 time for this batch 0.40096378326416016 ---------------------------------- train loss for this epoch: 0.212889
time for this epoch 58.295522928237915 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 113 # batch: 124 i_batch: 0.0 the loss for this batch: 0.24723035 flow loss 0.06261761 occ loss 0.18422268 time for this batch 0.2521324157714844 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.16015509 flow loss 0.0471026 occ loss 0.11274724 time for this batch 0.24814581871032715 ---------------------------------- train loss for this epoch: 0.214111
time for this epoch 41.10842943191528 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 114 # batch: 124 i_batch: 0.0 the loss for this batch: 0.24414706 flow loss 0.06352549 occ loss 0.18022478 time for this batch 0.34656786918640137 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.19031522 flow loss 0.053971242 occ loss 0.13598225 time for this batch 0.2336595058441162 ---------------------------------- train loss for this epoch: 0.213667
time for this epoch 44.37557649612427 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 115 # batch: 124 i_batch: 0.0 the loss for this batch: 0.18822406 flow loss 0.056590986 occ loss 0.13124214 time for this batch 0.32941126823425293 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.18674666 flow loss 0.054276988 occ loss 0.13207881 time for this batch 0.4092593193054199 ---------------------------------- train loss for this epoch: 0.213131
time for this epoch 59.95316767692566 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 116 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2657124 flow loss 0.07082158 occ loss 0.19416536 time for this batch 0.32158589363098145 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.1665719 flow loss 0.050768744 occ loss 0.11532974 time for this batch 0.34326982498168945 ---------------------------------- train loss for this epoch: 0.214013
time for this epoch 59.2137234210968 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 117 # batch: 124 i_batch: 0.0 the loss for this batch: 0.23465654 flow loss 0.06439703 occ loss 0.1696608 time for this batch 0.3290081024169922 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.19336456 flow loss 0.051385626 occ loss 0.14155245 time for this batch 0.3926842212677002 ---------------------------------- train loss for this epoch: 0.213361
time for this epoch 57.503268241882324 No_decrease: 3 ----------------an epoch starts------------------- i_epoch: 118 # batch: 124 i_batch: 0.0 the loss for this batch: 0.21789037 flow loss 0.055062406 occ loss 0.16250901 time for this batch 0.34218811988830566 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.1712883 flow loss 0.05041106 occ loss 0.12045927 time for this batch 0.4058713912963867 ---------------------------------- train loss for this epoch: 0.212852
time for this epoch 58.86929368972778 No_decrease: 4 ----------------an epoch starts------------------- i_epoch: 119 # batch: 124 i_batch: 0.0 the loss for this batch: 0.17528003 flow loss 0.053530283 occ loss 0.12130909 time for this batch 0.329134464263916 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.19667298 flow loss 0.051072173 occ loss 0.14512739 time for this batch 0.37235140800476074 ---------------------------------- train loss for this epoch: 0.212132
time for this epoch 56.851621866226196 No_decrease: 5 ----------------an epoch starts------------------- i_epoch: 120 # batch: 124 i_batch: 0.0 the loss for this batch: 0.25446582 flow loss 0.06374957 occ loss 0.19032268 time for this batch 0.33365964889526367 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.19475009 flow loss 0.050643656 occ loss 0.1436976 time for this batch 0.3743758201599121 ---------------------------------- train loss for this epoch: 0.212089
time for this epoch 58.11374640464783 No_decrease: 6 ----------------an epoch starts------------------- i_epoch: 121 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2357614 flow loss 0.06359565 occ loss 0.17152534 time for this batch 0.33023571968078613 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.26734248 flow loss 0.069599114 occ loss 0.19725154 time for this batch 0.3789551258087158 ---------------------------------- train loss for this epoch: 0.212328
time for this epoch 58.01237773895264 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 122 # batch: 124 i_batch: 0.0 the loss for this batch: 0.15853867 flow loss 0.045718953 occ loss 0.11240147 time for this batch 0.3401463031768799 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.22221285 flow loss 0.058982007 occ loss 0.16269185 time for this batch 0.3529651165008545 ---------------------------------- train loss for this epoch: 0.212162
time for this epoch 57.63170576095581 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 123 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2018946 flow loss 0.05559397 occ loss 0.14579919 time for this batch 0.33118128776550293 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.24008688 flow loss 0.064188465 occ loss 0.1755903 time for this batch 0.398700475692749 ---------------------------------- train loss for this epoch: 0.212483
time for this epoch 60.74751377105713 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 124 # batch: 124 i_batch: 0.0 the loss for this batch: 0.23245932 flow loss 0.06359074 occ loss 0.16794759 time for this batch 0.35729026794433594 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.19910087 flow loss 0.055807125 occ loss 0.14265375 time for this batch 0.42996883392333984 ---------------------------------- train loss for this epoch: 0.213169
time for this epoch 63.04020881652832 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 125 # batch: 124 i_batch: 0.0 the loss for this batch: 0.22786051 flow loss 0.058274772 occ loss 0.16921172 time for this batch 0.35199856758117676 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2356522 flow loss 0.060426358 occ loss 0.17442141 time for this batch 0.4379091262817383 ---------------------------------- train loss for this epoch: 0.211647
time for this epoch 62.66764259338379 No_decrease: 3 ----------------an epoch starts------------------- i_epoch: 126 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20944226 flow loss 0.053410828 occ loss 0.15555628 time for this batch 0.3602118492126465 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.17867535 flow loss 0.05169825 occ loss 0.12661529 time for this batch 0.40515661239624023 ---------------------------------- train loss for this epoch: 0.210516
time for this epoch 63.08777213096619 No_decrease: 4 ----------------an epoch starts------------------- i_epoch: 127 # batch: 124 i_batch: 0.0 the loss for this batch: 0.21900482 flow loss 0.057374638 occ loss 0.16118006 time for this batch 0.3616960048675537 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2811212 flow loss 0.07349326 occ loss 0.20681731 time for this batch 0.4117138385772705 ---------------------------------- train loss for this epoch: 0.211648
time for this epoch 61.78906559944153 No_decrease: 5 ----------------an epoch starts------------------- i_epoch: 128 # batch: 124 i_batch: 0.0 the loss for this batch: 0.25462466 flow loss 0.06884809 occ loss 0.18537186 time for this batch 0.3575119972229004 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2385649 flow loss 0.06152988 occ loss 0.17660514 time for this batch 0.4320363998413086 ---------------------------------- train loss for this epoch: 0.212408
time for this epoch 62.1650071144104 No_decrease: 6 ----------------an epoch starts------------------- i_epoch: 129 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20966715 flow loss 0.05590648 occ loss 0.15330873 time for this batch 0.34296655654907227 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.20963082 flow loss 0.055681325 occ loss 0.15350123 time for this batch 0.32584381103515625 ---------------------------------- train loss for this epoch: 0.211052
time for this epoch 60.519129276275635 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 130 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20142719 flow loss 0.055472672 occ loss 0.14551473 time for this batch 0.36144518852233887 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.22712024 flow loss 0.062241502 occ loss 0.16458537 time for this batch 0.4328653812408447 ---------------------------------- train loss for this epoch: 0.211388
time for this epoch 62.387415409088135 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 131 # batch: 124 i_batch: 0.0 the loss for this batch: 0.23723581 flow loss 0.06240287 occ loss 0.17456643 time for this batch 0.35629749298095703 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.21932074 flow loss 0.057142112 occ loss 0.16140407 time for this batch 0.36684489250183105 ---------------------------------- train loss for this epoch: 0.210213
time for this epoch 62.839929819107056 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 132 # batch: 124 i_batch: 0.0 the loss for this batch: 0.19222717 flow loss 0.050523326 occ loss 0.1413409 time for this batch 0.3603208065032959 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.21093296 flow loss 0.058264073 occ loss 0.15225379 time for this batch 0.4402194023132324 ---------------------------------- train loss for this epoch: 0.211404
time for this epoch 63.106489181518555 No_decrease: 3 ----------------an epoch starts------------------- i_epoch: 133 # batch: 124 i_batch: 0.0 the loss for this batch: 0.23303804 flow loss 0.0621917 occ loss 0.17029606 time for this batch 0.4035491943359375 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.18845928 flow loss 0.05603091 occ loss 0.13170275 time for this batch 0.374406099319458 ---------------------------------- train loss for this epoch: 0.211763
time for this epoch 57.71715831756592 No_decrease: 4 ----------------an epoch starts------------------- i_epoch: 134 # batch: 124 i_batch: 0.0 the loss for this batch: 0.25089344 flow loss 0.06378613 occ loss 0.18669736 time for this batch 0.34687089920043945 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.20964447 flow loss 0.05659702 occ loss 0.15271002 time for this batch 0.40065455436706543 ---------------------------------- train loss for this epoch: 0.211336
time for this epoch 57.46626615524292 No_decrease: 5 ----------------an epoch starts------------------- i_epoch: 135 # batch: 124 i_batch: 0.0 the loss for this batch: 0.12839548 flow loss 0.03917844 occ loss 0.08895057 time for this batch 0.3155517578125 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.20438705 flow loss 0.053216655 occ loss 0.15080306 time for this batch 0.3652007579803467 ---------------------------------- train loss for this epoch: 0.2109
time for this epoch 55.100343227386475 No_decrease: 6 ----------------an epoch starts------------------- i_epoch: 136 # batch: 124 i_batch: 0.0 the loss for this batch: 0.26169503 flow loss 0.07100421 occ loss 0.18998466 time for this batch 0.3195817470550537 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.20967239 flow loss 0.05539957 occ loss 0.15391056 time for this batch 0.44963574409484863 ---------------------------------- train loss for this epoch: 0.210661
time for this epoch 55.77916955947876 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 137 # batch: 124 i_batch: 0.0 the loss for this batch: 0.24145761 flow loss 0.066245355 occ loss 0.17486273 time for this batch 0.3163633346557617 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.23250966 flow loss 0.06107978 occ loss 0.17100084 time for this batch 0.4007406234741211 ---------------------------------- train loss for this epoch: 0.210148
time for this epoch 57.8660614490509 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 138 # batch: 124 i_batch: 0.0 the loss for this batch: 0.18655327 flow loss 0.051386498 occ loss 0.13448955 time for this batch 0.3242626190185547 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.17868944 flow loss 0.049291525 occ loss 0.12894908 time for this batch 0.3900940418243408 ---------------------------------- train loss for this epoch: 0.212791
time for this epoch 57.2260057926178 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 139 # batch: 124 i_batch: 0.0 the loss for this batch: 0.26305935 flow loss 0.065711804 occ loss 0.19675544 time for this batch 0.32539868354797363 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.15924144 flow loss 0.047835477 occ loss 0.11067772 time for this batch 0.3852198123931885 ---------------------------------- train loss for this epoch: 0.210379
time for this epoch 57.41444730758667 No_decrease: 3 ----------------an epoch starts------------------- i_epoch: 140 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20568128 flow loss 0.05638786 occ loss 0.14866269 time for this batch 0.33144092559814453 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2230156 flow loss 0.055464797 occ loss 0.16688587 time for this batch 0.3542160987854004 ---------------------------------- train loss for this epoch: 0.208321
time for this epoch 54.61547374725342 No_decrease: 4 ----------------an epoch starts------------------- i_epoch: 141 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20049901 flow loss 0.054868493 occ loss 0.14501147 time for this batch 0.33043932914733887 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.21153182 flow loss 0.055103827 occ loss 0.1559642 time for this batch 0.37822604179382324 ---------------------------------- train loss for this epoch: 0.209597
time for this epoch 55.94676470756531 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 142 # batch: 124 i_batch: 0.0 the loss for this batch: 0.23260796 flow loss 0.061640672 occ loss 0.17042412 time for this batch 0.38171958923339844 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.24828191 flow loss 0.061711617 occ loss 0.18611053 time for this batch 0.39584827423095703 ---------------------------------- train loss for this epoch: 0.208536
time for this epoch 60.954046964645386 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 143 # batch: 124 i_batch: 0.0 the loss for this batch: 0.18802483 flow loss 0.054637015 occ loss 0.1331015 time for this batch 0.3029594421386719 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.23589516 flow loss 0.062341034 occ loss 0.17311572 time for this batch 0.393918514251709 ---------------------------------- train loss for this epoch: 0.209314
time for this epoch 59.03946304321289 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 144 # batch: 124 i_batch: 0.0 the loss for this batch: 0.118708044 flow loss 0.03909263 occ loss 0.07850284 time for this batch 0.4381732940673828 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.18274121 flow loss 0.047567967 occ loss 0.13485233 time for this batch 0.4035453796386719 ---------------------------------- train loss for this epoch: 0.208598
time for this epoch 57.75765681266785 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 145 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2507744 flow loss 0.06310544 occ loss 0.1872768 time for this batch 0.2305889129638672 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.24802941 flow loss 0.06281773 occ loss 0.18450153 time for this batch 0.3968350887298584 ---------------------------------- train loss for this epoch: 0.209867
time for this epoch 55.47022008895874 No_decrease: 3 ----------------an epoch starts------------------- i_epoch: 146 # batch: 124 i_batch: 0.0 the loss for this batch: 0.29954812 flow loss 0.06921609 occ loss 0.22972772 time for this batch 0.3246889114379883 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.22500479 flow loss 0.0573374 occ loss 0.1668308 time for this batch 0.39711666107177734 ---------------------------------- train loss for this epoch: 0.20911
time for this epoch 56.8296856880188 No_decrease: 4 ----------------an epoch starts------------------- i_epoch: 147 # batch: 124 i_batch: 0.0 the loss for this batch: 0.25088832 flow loss 0.062490687 occ loss 0.1879457 time for this batch 0.32751035690307617 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2351153 flow loss 0.065643124 occ loss 0.16864873 time for this batch 0.35750532150268555 ---------------------------------- train loss for this epoch: 0.208525
time for this epoch 56.40230441093445 No_decrease: 5 ----------------an epoch starts------------------- i_epoch: 148 # batch: 124 i_batch: 0.0 the loss for this batch: 0.17811966 flow loss 0.04635173 occ loss 0.13132773 time for this batch 0.33146071434020996 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.24723853 flow loss 0.06250084 occ loss 0.18421838 time for this batch 0.3922460079193115 ---------------------------------- train loss for this epoch: 0.210477
time for this epoch 55.23791718482971 No_decrease: 6 ----------------an epoch starts------------------- i_epoch: 149 # batch: 124 i_batch: 0.0 the loss for this batch: 0.24258958 flow loss 0.06066562 occ loss 0.18086196 time for this batch 0.3640873432159424 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.17229806 flow loss 0.048743334 occ loss 0.12327089 time for this batch 0.38468265533447266 ---------------------------------- train loss for this epoch: 0.209135
time for this epoch 54.53561472892761 No_decrease: 7 ----------------an epoch starts------------------- i_epoch: 150 # batch: 124 i_batch: 0.0 the loss for this batch: 0.22544672 flow loss 0.05770968 occ loss 0.16728501 time for this batch 0.33144140243530273 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.18731081 flow loss 0.049349204 occ loss 0.13764594 time for this batch 0.377960205078125 ---------------------------------- train loss for this epoch: 0.202435
time for this epoch 52.38698768615723 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 151 # batch: 124 i_batch: 0.0 the loss for this batch: 0.17508927 flow loss 0.047447246 occ loss 0.12732676 time for this batch 0.3133730888366699 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.19363573 flow loss 0.05268562 occ loss 0.14049539 time for this batch 0.28293871879577637 ---------------------------------- train loss for this epoch: 0.201451
time for this epoch 57.03261470794678 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 152 # batch: 124 i_batch: 0.0 the loss for this batch: 0.26563343 flow loss 0.06594435 occ loss 0.19922738 time for this batch 0.3286252021789551 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.23037255 flow loss 0.0602396 occ loss 0.16946813 time for this batch 0.37340688705444336 ---------------------------------- train loss for this epoch: 0.200915
time for this epoch 56.174049377441406 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 153 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20124084 flow loss 0.052033015 occ loss 0.14890341 time for this batch 0.3166790008544922 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2519251 flow loss 0.06598279 occ loss 0.18527418 time for this batch 0.3811650276184082 ---------------------------------- train loss for this epoch: 0.200775
time for this epoch 58.469826221466064 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 154 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20889975 flow loss 0.053432237 occ loss 0.15502374 time for this batch 0.32251763343811035 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.22290191 flow loss 0.060060672 occ loss 0.1625975 time for this batch 0.3997325897216797 ---------------------------------- train loss for this epoch: 0.200893
time for this epoch 56.725106716156006 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 155 # batch: 124 i_batch: 0.0 the loss for this batch: 0.19274151 flow loss 0.049330827 occ loss 0.14290263 time for this batch 0.3756372928619385 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2405879 flow loss 0.062027548 occ loss 0.17813131 time for this batch 0.373929500579834 ---------------------------------- train loss for this epoch: 0.200564
time for this epoch 56.55095100402832 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 156 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20904471 flow loss 0.053231772 occ loss 0.15553063 time for this batch 0.31839919090270996 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.26152524 flow loss 0.062182486 occ loss 0.19885466 time for this batch 0.39647412300109863 ---------------------------------- train loss for this epoch: 0.20033
time for this epoch 55.876933336257935 No_decrease: 3 ----------------an epoch starts------------------- i_epoch: 157 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2024745 flow loss 0.052926965 occ loss 0.1490985 time for this batch 0.3296177387237549 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.19632286 flow loss 0.051903866 occ loss 0.14401366 time for this batch 0.37854623794555664 ---------------------------------- train loss for this epoch: 0.200437
time for this epoch 55.80081081390381 No_decrease: 4 ----------------an epoch starts------------------- i_epoch: 158 # batch: 124 i_batch: 0.0 the loss for this batch: 0.17137629 flow loss 0.044725366 occ loss 0.12636457 time for this batch 0.3051869869232178 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.22080636 flow loss 0.05838503 occ loss 0.16188744 time for this batch 0.3952903747558594 ---------------------------------- train loss for this epoch: 0.200193
time for this epoch 58.54358196258545 No_decrease: 5 ----------------an epoch starts------------------- i_epoch: 159 # batch: 124 i_batch: 0.0 the loss for this batch: 0.19230828 flow loss 0.05286432 occ loss 0.13920106 time for this batch 0.3206136226654053 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.19902703 flow loss 0.051997975 occ loss 0.14648339 time for this batch 0.3959314823150635 ---------------------------------- train loss for this epoch: 0.200717
time for this epoch 56.646005392074585 No_decrease: 6 ----------------an epoch starts------------------- i_epoch: 160 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2040258 flow loss 0.053250093 occ loss 0.15035458 time for this batch 0.3132593631744385 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.17942348 flow loss 0.04833226 occ loss 0.1305807 time for this batch 0.3535318374633789 ---------------------------------- train loss for this epoch: 0.200431
time for this epoch 54.9258553981781 No_decrease: 7 ----------------an epoch starts------------------- i_epoch: 161 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20021416 flow loss 0.056202143 occ loss 0.14349008 time for this batch 0.3282589912414551 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.1399902 flow loss 0.037202265 occ loss 0.10241886 time for this batch 0.3782074451446533 ---------------------------------- train loss for this epoch: 0.200429
time for this epoch 55.44337034225464 No_decrease: 8 ----------------an epoch starts------------------- i_epoch: 162 # batch: 124 i_batch: 0.0 the loss for this batch: 0.19886035 flow loss 0.05563831 occ loss 0.14292222 time for this batch 0.34711527824401855 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.17243548 flow loss 0.049807314 occ loss 0.12234077 time for this batch 0.3935377597808838 ---------------------------------- train loss for this epoch: 0.200075
time for this epoch 61.11107039451599 No_decrease: 9 ----------------an epoch starts------------------- i_epoch: 163 # batch: 124 i_batch: 0.0 the loss for this batch: 0.23114097 flow loss 0.061999347 occ loss 0.16866058 time for this batch 0.31491565704345703 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2809842 flow loss 0.069364846 occ loss 0.21109927 time for this batch 0.3996410369873047 ---------------------------------- train loss for this epoch: 0.199811
time for this epoch 58.52831983566284 No_decrease: 10 ----------------an epoch starts------------------- i_epoch: 164 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2834407 flow loss 0.06690343 occ loss 0.21584778 time for this batch 0.3237423896789551 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.24472028 flow loss 0.06297133 occ loss 0.18131305 time for this batch 0.3737924098968506 ---------------------------------- train loss for this epoch: 0.199962
time for this epoch 56.210179805755615 No_decrease: 11 ----------------an epoch starts------------------- i_epoch: 165 # batch: 124 i_batch: 0.0 the loss for this batch: 0.17034414 flow loss 0.048383396 occ loss 0.12149709 time for this batch 0.33112406730651855 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.21689038 flow loss 0.05453071 occ loss 0.16199881 time for this batch 0.29999828338623047 ---------------------------------- train loss for this epoch: 0.199825
time for this epoch 55.738481760025024 No_decrease: 12 ----------------an epoch starts------------------- i_epoch: 166 # batch: 124 i_batch: 0.0 the loss for this batch: 0.10772258 flow loss 0.03342322 occ loss 0.07410841 time for this batch 0.31736326217651367 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.19441256 flow loss 0.05440215 occ loss 0.1395647 time for this batch 0.39225006103515625 ---------------------------------- train loss for this epoch: 0.199518
time for this epoch 56.08292603492737 No_decrease: 13 ----------------an epoch starts------------------- i_epoch: 167 # batch: 124 i_batch: 0.0 the loss for this batch: 0.15875356 flow loss 0.045137875 occ loss 0.1133022 time for this batch 0.3229942321777344 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.19465214 flow loss 0.052872855 occ loss 0.14145398 time for this batch 0.36229658126831055 ---------------------------------- train loss for this epoch: 0.200107
time for this epoch 56.11011481285095 No_decrease: 14 ----------------an epoch starts------------------- i_epoch: 168 # batch: 124 i_batch: 0.0 the loss for this batch: 0.21879724 flow loss 0.05786957 occ loss 0.16057618 time for this batch 0.31800079345703125 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2172382 flow loss 0.053359993 occ loss 0.16337526 time for this batch 0.3501579761505127 ---------------------------------- train loss for this epoch: 0.200058
time for this epoch 55.60925602912903 No_decrease: 15 ----------------an epoch starts------------------- i_epoch: 169 # batch: 124 i_batch: 0.0 the loss for this batch: 0.1808788 flow loss 0.048703298 occ loss 0.13191599 time for this batch 0.3301239013671875 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2199905 flow loss 0.058485154 occ loss 0.1611257 time for this batch 0.311176061630249 ---------------------------------- train loss for this epoch: 0.199617
time for this epoch 54.43928098678589 No_decrease: 16 ----------------an epoch starts------------------- i_epoch: 170 # batch: 124 i_batch: 0.0 the loss for this batch: 0.21177006 flow loss 0.054368496 occ loss 0.15688673 time for this batch 0.328113317489624 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.14446528 flow loss 0.03993397 occ loss 0.10417684 time for this batch 0.40082573890686035 ---------------------------------- train loss for this epoch: 0.199684
time for this epoch 58.476709604263306 No_decrease: 17 ----------------an epoch starts------------------- i_epoch: 171 # batch: 124 i_batch: 0.0 the loss for this batch: 0.19083975 flow loss 0.055276893 occ loss 0.1352184 time for this batch 0.3612687587738037 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.19561857 flow loss 0.054166567 occ loss 0.14100814 time for this batch 0.35644960403442383 ---------------------------------- train loss for this epoch: 0.199521
time for this epoch 57.135366678237915 No_decrease: 18 ----------------an epoch starts------------------- i_epoch: 172 # batch: 124 i_batch: 0.0 the loss for this batch: 0.1928622 flow loss 0.051509194 occ loss 0.14107038 time for this batch 0.3701510429382324 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.19597591 flow loss 0.046939213 occ loss 0.14872263 time for this batch 0.38524365425109863 ---------------------------------- train loss for this epoch: 0.200151
time for this epoch 59.76276922225952 No_decrease: 19 ----------------an epoch starts------------------- i_epoch: 173 # batch: 124 i_batch: 0.0 the loss for this batch: 0.1845787 flow loss 0.04765564 occ loss 0.13638231 time for this batch 0.3559544086456299 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.17295474 flow loss 0.047152232 occ loss 0.12546195 time for this batch 0.4039750099182129 ---------------------------------- train loss for this epoch: 0.199408
time for this epoch 63.36862087249756 No_decrease: 20 ----------------an epoch starts------------------- i_epoch: 174 # batch: 124 i_batch: 0.0 the loss for this batch: 0.22580706 flow loss 0.05823025 occ loss 0.16712044 time for this batch 0.31988024711608887 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.17894198 flow loss 0.044487398 occ loss 0.13414462 time for this batch 0.3731677532196045 ---------------------------------- train loss for this epoch: 0.199229
time for this epoch 55.58278465270996 No_decrease: 21 ----------------an epoch starts------------------- i_epoch: 175 # batch: 124 i_batch: 0.0 the loss for this batch: 0.17280304 flow loss 0.046749987 occ loss 0.12570395 time for this batch 0.3219294548034668 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.22283792 flow loss 0.060657848 occ loss 0.16156921 time for this batch 0.3425319194793701 ---------------------------------- train loss for this epoch: 0.199232
time for this epoch 57.008519887924194 No_decrease: 22 ----------------an epoch starts------------------- i_epoch: 176 # batch: 124 i_batch: 0.0 the loss for this batch: 0.18974896 flow loss 0.05080864 occ loss 0.13866563 time for this batch 0.2302708625793457 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.14368291 flow loss 0.039795715 occ loss 0.10368629 time for this batch 0.3527047634124756 ---------------------------------- train loss for this epoch: 0.199424
time for this epoch 54.17574906349182 No_decrease: 23 ----------------an epoch starts------------------- i_epoch: 177 # batch: 124 i_batch: 0.0 the loss for this batch: 0.1768179 flow loss 0.049606007 occ loss 0.12684333 time for this batch 0.31728219985961914 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.27652803 flow loss 0.06752767 occ loss 0.20860232 time for this batch 0.3870093822479248 ---------------------------------- train loss for this epoch: 0.200167
time for this epoch 56.26906442642212 No_decrease: 24 ----------------an epoch starts------------------- i_epoch: 178 # batch: 124 i_batch: 0.0 the loss for this batch: 0.14798017 flow loss 0.040723022 occ loss 0.106731944 time for this batch 0.36989784240722656 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.25925997 flow loss 0.06367692 occ loss 0.19512664 time for this batch 0.40022897720336914 ---------------------------------- train loss for this epoch: 0.199341
time for this epoch 58.61595916748047 No_decrease: 25 ----------------an epoch starts------------------- i_epoch: 179 # batch: 124 i_batch: 0.0 the loss for this batch: 0.21903257 flow loss 0.058848016 occ loss 0.15949906 time for this batch 0.3302037715911865 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.20683789 flow loss 0.05416989 occ loss 0.1523794 time for this batch 0.37154459953308105 ---------------------------------- train loss for this epoch: 0.199141
time for this epoch 55.49847769737244 No_decrease: 26 ----------------an epoch starts------------------- i_epoch: 180 # batch: 124 i_batch: 0.0 the loss for this batch: 0.19200328 flow loss 0.05027941 occ loss 0.14131056 time for this batch 0.307861328125 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.20549263 flow loss 0.05606951 occ loss 0.14910114 time for this batch 0.3742406368255615 ---------------------------------- train loss for this epoch: 0.199216
time for this epoch 55.968082666397095 No_decrease: 27 ----------------an epoch starts------------------- i_epoch: 181 # batch: 124 i_batch: 0.0 the loss for this batch: 0.16034037 flow loss 0.043130234 occ loss 0.11686816 time for this batch 0.3193199634552002 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.23929529 flow loss 0.06061436 occ loss 0.17818958 time for this batch 0.39344072341918945 ---------------------------------- train loss for this epoch: 0.199083
time for this epoch 55.5471670627594 No_decrease: 28 ----------------an epoch starts------------------- i_epoch: 182 # batch: 124 i_batch: 0.0 the loss for this batch: 0.15563929 flow loss 0.041567057 occ loss 0.11375057 time for this batch 0.3339273929595947 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.15054493 flow loss 0.04300888 occ loss 0.10729003 time for this batch 0.3837265968322754 ---------------------------------- train loss for this epoch: 0.199246
time for this epoch 56.56777548789978 No_decrease: 29 ----------------an epoch starts------------------- i_epoch: 183 # batch: 124 i_batch: 0.0 the loss for this batch: 0.23317528 flow loss 0.055783752 occ loss 0.17700909 time for this batch 0.33321380615234375 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.19953547 flow loss 0.052990597 occ loss 0.1462005 time for this batch 0.3809478282928467 ---------------------------------- train loss for this epoch: 0.198932
time for this epoch 57.19133543968201 Early stop at the 184-th epoch
def apply_to_vali_test(model, vt, f_o_mean_std):
f = vt["flow"]
f_m = vt["flow_mask"].to(device)
o = vt["occupancy"]
o_m = vt["occupancy_mask"].to(device)
f_mae, f_rmse, o_mae, o_rmse = vali_test(model, f, f_m, o, o_m, f_o_mean_std, hyper["b_s_vt"])
print ("flow_mae", f_mae)
print ("flow_rmse", f_rmse)
print ("occ_mae", o_mae)
print ("occ_rmse", o_rmse)
return f_mae, f_rmse, o_mae, o_rmse
vali_f_mae, vali_f_rmse, vali_o_mae, vali_o_rmse =\
apply_to_vali_test(trained_model, vali, f_o_mean_std)
flow_mae 34.83063394313236 flow_rmse 53.87441952162064 occ_mae 0.03831921818638007 occ_rmse 0.07841136881949592
test_f_mae, test_f_rmse, test_o_mae, test_o_rmse =\
apply_to_vali_test(trained_model, test, f_o_mean_std)
flow_mae 33.03770116332661 flow_rmse 51.03821776888166 occ_mae 0.0314599494901205 occ_rmse 0.06736482214882997